COORDINATED ACCESS TO A FILE SYSTEM'S SHARED STORAGE USING DYNAMIC CREATION OF FILE ACCESS LAYOUT

• US 20140095582A1
• Filed: 09/28/2012
• Published: 04/03/2014
• Est. Priority Date: 09/28/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: ESHEL, MARC, HILDEBRAND, DEAN, SCHMUCK, FRANK B., WYLLIE, JAMES C.
• Granted Patent: US 9,727,578 B2
• Time in Patent Office: Days
• US Class Current: 709/203
• CPC Class Codes: G06F 16/182 Distributed file systems
• CPC Class Codes: G06F 16/183 Provision of network file services by network file servers, e.g. by using NFS, CIFS network file access protocols H04L67/1097
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0635 by changing the path, e.g. traffic rerouting, path reconfiguration
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

Embodiments of the invention relate to supporting coordinated access to a clustered file system'"'"'s shared disk storage subsystem by using dynamic creation of file access layout for different workloads and access patterns. Active file servers in the cluster have equivalent access to shared data of said file system. In one embodiment, a particular file server in the cluster is configured to coordinate the file system'"'"'s layout. The particular file server, in response to a particular client'"'"'s request for a layout of a file stored by said file system in said subsystem determines a file access layout for a parallel file access protocol to use when servicing an I/O request by said client, marks said layout as active for the client, and sends the layout to the client. The file access layout is determined based on one or more of current file system resources, a specific workload type and a specific byte-range of the file included in the client request, and properties of the file. The layout includes a set of file servers in said cluster and byte ranges of the file, and the byte-range being associated with a particular server among the set.

Claims

1. A method of supporting coordinated access to a clustered file system'"'"'s shared disk storage subsystem by using dynamic creation of file access layout for different workloads and access patterns, wherein active file servers in said cluster have equivalent access to shared data of said file system, the method comprising:

in response to a particular file based parallel file access protocol client'"'"'s request for a file access layout of a file stored by said file system in said subsystem, determining a file access layout for a parallel file access protocol to use when servicing an I/O request by said client;

wherein, said determining is based on one or more of;

(i) current file system resources, (ii) a specific workload type and a specific byte-range of the file included in the client request, and (iii) properties of the file, and said layout includes a set of file servers in said cluster and byte ranges of the file, and the byte-range being associated with a particular server among said set;

marking said layout as active for the client; and

sending said layout to the client.

2. The method of claim 1, further comprising:

receiving a returned file access layout from the client; and

marking the layout as inactive for the client.

3. The method of claim 1, further comprising:

adding a new file server to said file system such that a client'"'"'s request for a file access layout includes the added file server in the determined file access layout; and

wherein, for clients that have mounted said file system, if;

(i) a client has a cached file access layout, and (ii) the cached file access layout is not active, then invalidating the client'"'"'s file access layout such that the next time the client performs I/O the client will retrieve a new file access layout from said file system.

4. The method of claim 1, further comprising:

adding a new file server to said file system such that a client'"'"'s request for a file access layout includes the added file server in the determined file access layout; and

wherein, for clients that have mounted said file system, if;

(i) a client has a cached file access layout, and (ii) the cached file access layout is active, then invalidating the client'"'"'s file access layout after the client node has returned the active file access layout to said file system.

5. The method of claim 1, further comprising:

removing a file server from said file system such that a client'"'"'s request for a file access layout does not include the removed file server in the determined file access layout; and

wherein, for clients that have mounted said file system, if a client has an active or inactive file access layout, then determining a new layout for the client that does not include the server that was removed.

6. The method of claim 1, further comprising:

upon a file server'"'"'s failure, having a different file server service a client'"'"'s I/O request(s); and

wherein, for clients that have mounted said file system, if a client has an active or inactive file access layout, then removing the file server from the client'"'"'s file access layout.

7. The method of claim 1, wherein said resources are selected from the group consisting of:

(i) available file servers, (ii) available network bandwidth, (iii) available storage bandwidth, (iv) open file system connections, (v) processing unit resources, (vi) number of clients currently accessing the file, and (vii) number and type of existing active file access layouts for the file.

8. The method of claim 1, wherein said resources are determined by monitoring active file servers in said cluster.

9. The method of claim 8, wherein said file system, to perform said monitoring, runs an I/O bandwidth optimization algorithm service to determine an aggregate number of file servers and byte ranges for each server to serve requests to the file.

10. The method of claim 1, further comprising:

upon receiving an write request from a client, validating that byte-range to be written complies with the file access layout that was sent to the client; and

writing the data to said storage subsystem.

11. The method of claim 1, further comprising:

upon receiving a read request from a client, validating that byte-range to be read complies with the file access layout that was sent the client; and

reading the data from the clustered file system'"'"'s shared disk storage subsystem and sending said data to the client.

12. The method of claim 1, wherein said resources are from monitoring active file servers in said cluster.

13. The method of claim 1, wherein said determining, of the file access layout for a parallel file access protocol to use when servicing an I/O request by said client, is such that said client optimally utilizes available hardware and software resources for the I/O request.

14. A file system of supporting coordinated access to said file system'"'"'s shared disk storage subsystem by using dynamic creation of file access layout for different workloads and access patterns, said file system comprising:

a shared disk storage subsystem that stores said file system'"'"'s shared data;

a plurality of file servers in a cluster, each of the file servers that are active having equivalent access to the shared data, wherein a particular file server among said servers is configured to coordinate the file system'"'"'s layout;

wherein the particular file server, in response to a particular client'"'"'s request for a file access layout of a file stored by said file system in said subsystem;

(i) determines a file access layout for a parallel file access protocol to use when servicing an I/O request by said client, (ii) marks said layout as active for the client, and (iii) sends said layout to the client; and

wherein, the file access layout is determined based on one or more of;

(i) current file system resources, (ii) a specific workload type and a specific byte-range of the file included in the client request, and (iii) properties of the file, and said layout includes a set of file servers in said cluster and byte ranges of the file, and the byte-range being associated with a particular server among said set.

15. A computer program product of supporting coordinated access to a clustered file system'"'"'s shared disk storage subsystem by using dynamic creation of file access layout for different workloads and access patterns, wherein active file servers in said cluster have equivalent access to shared data of said file system, said program product comprising a computer readable storage medium having computer usable program code embodied therewith, said program code being readable/executable by a file system to:

in response to a particular client'"'"'s request for a file access layout of a file stored by said file system in said subsystem, determine a file access layout for a parallel file access protocol to use when servicing an I/O request by said client;

wherein, said file access layout is determined based on one or more of;

(i) current file system resources, (ii) a specific workload type and a specific byte-range of the file included in the client request, and (iii) properties of the file, and said layout includes a set of file servers in said cluster and byte ranges of the file, and the byte-range being associated with a particular server among said set;

mark said layout as active for the client; and

send said layout to the client.

16. The computer program product of claim 15, said program code being further configured to:

receive a returned file access layout from the client; and

mark the layout as inactive for the client.

17. The computer program product of claim 15, said program code being further configured to:

add a new file server to said file system such that a client'"'"'s request for a file access layout includes the added file server in the determined file access layout; and

wherein, for clients that have mounted said file system, if;

(i) a client has a cached file access layout, and (ii) the cached file access layout is not active, then invalidate the client'"'"'s file access layout such that the next time the client performs I/O the client will retrieve a new file access layout from said file system.

18. The computer program product of claim 15, said program code being further configured to:

add a new file server to said file system such that a client'"'"'s request for a file access layout includes the added file server in the determined file access layout; and

wherein, for clients that have mounted said file system, if;

(i) a client has a cached file access layout, and (ii) the cached file access layout is active, then invalidate the client'"'"'s file access layout after the client node has returned the active file access layout to said file system.

19. The computer program product of claim 15, said program code being further configured to:

remove a file server from said file system such that a client'"'"'s request for a file access layout does not include the removed file server in the determined file access layout; and

wherein, for clients that have mounted said file system, if a client has an active or inactive file access layout, then determine a new layout for the client that does not include the server that was removed.

20. The computer program product of claim 15, said program code being further configured to:

upon a file server'"'"'s failure, have a different file server service a client'"'"'s I/O request(s); and

wherein, for clients that have mounted said file system, if a client has an active or inactive file access layout, then remove the file server from the client'"'"'s file access layout.

21. The computer program product of claim 15, said program code being further configured to:

upon receiving an write request from a client, validate that the byte-range to be written complies with the file access layout that was sent to the client; and

write the data to said storage subsystem.

22. The computer program product of claim 15, said program code being further configured to:

upon receiving a read request from a client, validating that the byte-range to be read complies with the file access layout that was sent the client; and

reading the data from the clustered file system'"'"'s shared disk storage subsystem and sending said data to the client.